agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v28 09/11] Add support for min/max aggregates for IVM 259+ messages / 2 participants [nested] [flat]
* [PATCH v28 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index c8aa558f2e..c40ea6b2bc 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1312,6 +1312,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index aa6bf2694a..fa65e4aeb0 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -73,6 +73,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + OverrideSearchPath *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -109,6 +137,7 @@ typedef struct MV_TriggerTable TupleTableSlot *slot; /* for checking visibility in the pre-state table */ } MV_TriggerTable; +static HTAB *mv_query_cache = NULL; static HTAB *mv_trigger_info = NULL; static bool in_delta_calculation = false; @@ -169,6 +198,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -177,17 +209,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort); /* @@ -2102,6 +2147,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2183,6 +2230,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2212,6 +2270,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2230,10 +2290,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2425,6 +2493,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2527,19 +2659,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2554,10 +2711,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2565,10 +2723,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2751,6 +2924,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -2784,6 +3300,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -2792,6 +3315,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + OverrideSearchPathMatchesCurrent(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetOverrideSearchPath(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.25.1 --Multipart=_Thu__1_Jun_2023_23_59_09_+0900_/G5+8nG46.f1T42K Content-Type: text/x-diff; name="v28-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Disposition: attachment; filename="v28-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Transfer-Encoding: 7bit ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v37 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 45a30309951..ed67f399b7c 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1332,6 +1332,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Fri__29_May_2026_23_14_17_+0900_Te0o73X2VqYK57Gd Content-Type: text/x-diff; name="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v37-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v38 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index 35e124694ab..540d9e3d5c8 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1341,6 +1341,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 710224aa994..3b3871c49e2 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -121,6 +149,7 @@ typedef struct DroppedImmvInfo } DroppedImmvInfo; static HTAB *mv_trigger_info = NULL; +static HTAB *mv_query_cache = NULL; static HTAB *dropped_immv = NULL; static HTAB *LastIvmUpdateHash; @@ -210,6 +239,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -218,17 +250,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort, SubTransactionId subxid); static void setLastUpdateXid(Oid immv_oid, FullTransactionId xid); @@ -2343,6 +2388,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2424,6 +2471,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2453,6 +2511,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2471,10 +2531,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2666,6 +2734,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2768,19 +2900,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2795,10 +2952,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2806,10 +2964,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2992,6 +3165,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -3025,6 +3541,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -3039,6 +3562,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.43.0 --Multipart=_Wed__1_Jul_2026_00_04_01_+0900_OVSy2WWK_9aByzDJ Content-Type: text/x-diff; name="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v38-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v33 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index d8767137d9..abce06d046 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1309,6 +1309,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 97406b28c9..0ff5e3922b 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -105,6 +133,7 @@ typedef struct MV_TriggerTable TupleTableSlot *slot; /* for checking visibility in the pre-state table */ } MV_TriggerTable; +static HTAB *mv_query_cache = NULL; static HTAB *mv_trigger_info = NULL; static bool in_delta_calculation = false; @@ -165,6 +194,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -173,17 +205,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort); /* @@ -2122,6 +2167,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2203,6 +2250,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2232,6 +2290,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2250,10 +2310,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2445,6 +2513,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2547,19 +2679,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2574,10 +2731,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2585,10 +2743,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2771,6 +2944,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -2804,6 +3320,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -2812,6 +3335,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.25.1 --Multipart=_Tue__2_Jul_2024_17_03_11_+0900_6OrVBZxOB4o_k6A1 Content-Type: text/x-diff; name="v33-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v33-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v32 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index ecec93ec1c..d3cf3df5a7 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1311,6 +1311,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index b7f6c3831b..42ff0ed98f 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -105,6 +133,7 @@ typedef struct MV_TriggerTable TupleTableSlot *slot; /* for checking visibility in the pre-state table */ } MV_TriggerTable; +static HTAB *mv_query_cache = NULL; static HTAB *mv_trigger_info = NULL; static bool in_delta_calculation = false; @@ -165,6 +194,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -173,17 +205,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort); /* @@ -2124,6 +2169,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2205,6 +2252,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2234,6 +2292,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2252,10 +2312,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2447,6 +2515,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2549,19 +2681,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2576,10 +2733,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2587,10 +2745,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2773,6 +2946,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -2806,6 +3322,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -2814,6 +3337,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.25.1 --Multipart=_Sun__31_Mar_2024_22_59_31_+0900_msknEviJj08_wgqO Content-Type: text/x-diff; name="v32-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Disposition: attachment; filename="v32-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Transfer-Encoding: 7bit ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v34 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index d8767137d9..abce06d046 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1309,6 +1309,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index ca6d236989..8cd7ed3b68 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -105,6 +133,7 @@ typedef struct MV_TriggerTable TupleTableSlot *slot; /* for checking visibility in the pre-state table */ } MV_TriggerTable; +static HTAB *mv_query_cache = NULL; static HTAB *mv_trigger_info = NULL; static bool in_delta_calculation = false; @@ -165,6 +194,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -173,17 +205,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort); /* @@ -2124,6 +2169,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2205,6 +2252,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2234,6 +2292,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2252,10 +2312,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2447,6 +2515,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2549,19 +2681,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2576,10 +2733,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2587,10 +2745,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2773,6 +2946,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -2806,6 +3322,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -2814,6 +3337,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.34.1 --Multipart=_Thu__11_Jul_2024_13_23_57_+0900_hKsU2G3a3BgS2FFs Content-Type: text/x-diff; name="v34-0008-Add-aggregates-support-in-IVM.patch" Content-Disposition: attachment; filename="v34-0008-Add-aggregates-support-in-IVM.patch" Content-Transfer-Encoding: quoted-printable ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v30 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index d93eec3eec..0536e44b9e 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1312,6 +1312,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 3c523991ed..e60f92226c 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -73,6 +73,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -109,6 +137,7 @@ typedef struct MV_TriggerTable TupleTableSlot *slot; /* for checking visibility in the pre-state table */ } MV_TriggerTable; +static HTAB *mv_query_cache = NULL; static HTAB *mv_trigger_info = NULL; static bool in_delta_calculation = false; @@ -169,6 +198,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -177,17 +209,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort); /* @@ -2123,6 +2168,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2204,6 +2251,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2233,6 +2291,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2251,10 +2311,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2446,6 +2514,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2548,19 +2680,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2575,10 +2732,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2586,10 +2744,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2772,6 +2945,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -2805,6 +3321,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -2813,6 +3336,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.25.1 --Multipart=_Mon__4_Mar_2024_11_58_46_+0900_UaponF/qQhQrVCFt Content-Type: text/x-diff; name="v30-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Disposition: attachment; filename="v30-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Transfer-Encoding: 7bit ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v31 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index aa8440b4e1..7e1627ad1b 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1309,6 +1309,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index 97406b28c9..0ff5e3922b 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -69,6 +69,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -105,6 +133,7 @@ typedef struct MV_TriggerTable TupleTableSlot *slot; /* for checking visibility in the pre-state table */ } MV_TriggerTable; +static HTAB *mv_query_cache = NULL; static HTAB *mv_trigger_info = NULL; static bool in_delta_calculation = false; @@ -165,6 +194,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -173,17 +205,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort); /* @@ -2122,6 +2167,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2203,6 +2250,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2232,6 +2290,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2250,10 +2310,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2445,6 +2513,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2547,19 +2679,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2574,10 +2731,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2585,10 +2743,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2771,6 +2944,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -2804,6 +3320,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -2812,6 +3335,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.25.1 --Multipart=_Fri__29_Mar_2024_23_47_00_+0900_KGpmmDOIs1266Ib1 Content-Type: text/x-diff; name="v31-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Disposition: attachment; filename="v31-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Transfer-Encoding: 7bit ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v29 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index c8aa558f2e..c40ea6b2bc 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1312,6 +1312,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index ee41f0007d..eff512d40c 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -73,6 +73,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -109,6 +137,7 @@ typedef struct MV_TriggerTable TupleTableSlot *slot; /* for checking visibility in the pre-state table */ } MV_TriggerTable; +static HTAB *mv_query_cache = NULL; static HTAB *mv_trigger_info = NULL; static bool in_delta_calculation = false; @@ -169,6 +198,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -177,17 +209,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort); /* @@ -2101,6 +2146,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2182,6 +2229,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2211,6 +2269,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2229,10 +2289,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2424,6 +2492,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2526,19 +2658,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2553,10 +2710,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2564,10 +2722,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2750,6 +2923,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -2783,6 +3299,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -2791,6 +3314,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.25.1 --Multipart=_Mon__28_Aug_2023_11_52_52_+0900_hj6L5h176QaSGtg7 Content-Type: text/x-diff; name="v29-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Disposition: attachment; filename="v29-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Transfer-Encoding: 7bit ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v29 09/11] Add support for min/max aggregates for IVM @ 2023-05-31 11:58 Yugo Nagata <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Yugo Nagata @ 2023-05-31 11:58 UTC (permalink / raw) Supporting min and max is more complicated than count, sum, or avg. For an example of min, when tuples are inserted, the current min value in the view and the min value in the inseteted tuples are compared, then the smaller one is used as the latest min value. On the other hand, when tuples are deleted, if the current min value in the view equals to the min in the deleted tuples, we need re-computation the latest min value from base tables. Otherwise, the current value in the view remains. --- src/backend/commands/createas.c | 45 +++ src/backend/commands/matview.c | 644 +++++++++++++++++++++++++++++++- 2 files changed, 680 insertions(+), 9 deletions(-) diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c index c8aa558f2e..c40ea6b2bc 100644 --- a/src/backend/commands/createas.c +++ b/src/backend/commands/createas.c @@ -1312,6 +1312,51 @@ check_aggregate_supports_ivm(Oid aggfnoid) case F_AVG_FLOAT8: case F_AVG_INTERVAL: + /* min */ + case F_MIN_ANYARRAY: + case F_MIN_INT8: + case F_MIN_INT4: + case F_MIN_INT2: + case F_MIN_OID: + case F_MIN_FLOAT4: + case F_MIN_FLOAT8: + case F_MIN_DATE: + case F_MIN_TIME: + case F_MIN_TIMETZ: + case F_MIN_MONEY: + case F_MIN_TIMESTAMP: + case F_MIN_TIMESTAMPTZ: + case F_MIN_INTERVAL: + case F_MIN_TEXT: + case F_MIN_NUMERIC: + case F_MIN_BPCHAR: + case F_MIN_TID: + case F_MIN_ANYENUM: + case F_MIN_INET: + case F_MIN_PG_LSN: + + /* max */ + case F_MAX_ANYARRAY: + case F_MAX_INT8: + case F_MAX_INT4: + case F_MAX_INT2: + case F_MAX_OID: + case F_MAX_FLOAT4: + case F_MAX_FLOAT8: + case F_MAX_DATE: + case F_MAX_TIME: + case F_MAX_TIMETZ: + case F_MAX_MONEY: + case F_MAX_TIMESTAMP: + case F_MAX_TIMESTAMPTZ: + case F_MAX_INTERVAL: + case F_MAX_TEXT: + case F_MAX_NUMERIC: + case F_MAX_BPCHAR: + case F_MAX_TID: + case F_MAX_ANYENUM: + case F_MAX_INET: + case F_MAX_PG_LSN: return true; default: diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c index ee41f0007d..eff512d40c 100644 --- a/src/backend/commands/matview.c +++ b/src/backend/commands/matview.c @@ -73,6 +73,34 @@ typedef struct #define MV_INIT_QUERYHASHSIZE 16 +/* MV query type codes */ +#define MV_PLAN_RECALC 1 +#define MV_PLAN_SET_VALUE 2 + +/* + * MI_QueryKey + * + * The key identifying a prepared SPI plan in our query hashtable + */ +typedef struct MV_QueryKey +{ + Oid matview_id; /* OID of materialized view */ + int32 query_type; /* query type ID, see MV_PLAN_XXX above */ +} MV_QueryKey; + +/* + * MV_QueryHashEntry + * + * Hash entry for cached plans used to maintain materialized views. + */ +typedef struct MV_QueryHashEntry +{ + MV_QueryKey key; + SPIPlanPtr plan; + SearchPathMatcher *search_path; /* search_path used for parsing + * and planning */ +} MV_QueryHashEntry; + /* * MV_TriggerHashEntry * @@ -109,6 +137,7 @@ typedef struct MV_TriggerTable TupleTableSlot *slot; /* for checking visibility in the pre-state table */ } MV_TriggerTable; +static HTAB *mv_query_cache = NULL; static HTAB *mv_trigger_info = NULL; static bool in_delta_calculation = false; @@ -169,6 +198,9 @@ static void append_set_clause_for_sum(const char *resname, StringInfo buf_old, static void append_set_clause_for_avg(const char *resname, StringInfo buf_old, StringInfo buf_new, StringInfo aggs_list, const char *aggtype); +static void append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min); static char *get_operation_string(IvmOp op, const char *col, const char *arg1, const char *arg2, const char* count_col, const char *castType); static char *get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, @@ -177,17 +209,30 @@ static void apply_old_delta(const char *matviewname, const char *deltaname_old, List *keys); static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname); + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc); static void apply_new_delta(const char *matviewname, const char *deltaname_new, StringInfo target_list); static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new, List *keys, StringInfo target_list, StringInfo aggs_set, const char* count_colname); static char *get_matching_condition_string(List *keys); +static char *get_returning_string(List *minmax_list, List *is_min_list, List *keys); +static char *get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list); +static char *get_select_for_recalc_string(List *keys); +static void recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel); +static SPIPlanPtr get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes); +static SPIPlanPtr get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes); static void generate_equal(StringInfo querybuf, Oid opttype, const char *leftop, const char *rightop); static void mv_InitHashTables(void); +static SPIPlanPtr mv_FetchPreparedPlan(MV_QueryKey *key); +static void mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan); +static void mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type); static void clean_up_IVM_hash_entry(MV_TriggerHashEntry *entry, bool is_abort); /* @@ -2101,6 +2146,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n ListCell *lc; int i; List *keys = NIL; + List *minmax_list = NIL; + List *is_min_list = NIL; /* @@ -2182,6 +2229,17 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n append_set_clause_for_avg(resname, aggs_set_old, aggs_set_new, aggs_list_buf, format_type_be(aggref->aggtype)); + /* min/max */ + else if (!strcmp(aggname, "min") || !strcmp(aggname, "max")) + { + bool is_min = (!strcmp(aggname, "min")); + + append_set_clause_for_minmax(resname, aggs_set_old, aggs_set_new, aggs_list_buf, is_min); + + /* make a resname list of min and max aggregates */ + minmax_list = lappend(minmax_list, resname); + is_min_list = lappend_int(is_min_list, is_min); + } else elog(ERROR, "unsupported aggregate function: %s", aggname); } @@ -2211,6 +2269,8 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n if (old_tuplestores && tuplestore_tuple_count(old_tuplestores) > 0) { EphemeralNamedRelation enr = palloc(sizeof(EphemeralNamedRelationData)); + SPITupleTable *tuptable_recalc = NULL; + uint64 num_recalc; int rc; /* convert tuplestores to ENR, and register for SPI */ @@ -2229,10 +2289,18 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n /* apply old delta and get rows to be recalculated */ apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME, keys, aggs_list_buf, aggs_set_old, - count_colname); + minmax_list, is_min_list, + count_colname, &tuptable_recalc, &num_recalc); else apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys); + /* + * If we have min or max, we might have to recalculate aggregate values from base tables + * on some tuples. TIDs and keys such tuples are returned as a result of the above query. + */ + if (minmax_list && tuptable_recalc) + recalc_and_set_values(tuptable_recalc, num_recalc, minmax_list, keys, matviewRel); + } /* For tuple insertion */ if (new_tuplestores && tuplestore_tuple_count(new_tuplestores) > 0) @@ -2424,6 +2492,70 @@ append_set_clause_for_avg(const char *resname, StringInfo buf_old, ); } +/* + * append_set_clause_for_minmax + * + * Append SET clause string for min or max aggregation to given buffers. + * Also, append resnames required for calculating the aggregate value. + * is_min is true if this is min, false if not. + */ +static void +append_set_clause_for_minmax(const char *resname, StringInfo buf_old, + StringInfo buf_new, StringInfo aggs_list, + bool is_min) +{ + char *count_col = IVM_colname("count", resname); + + /* For tuple deletion */ + if (buf_old) + { + /* + * If the new value doesn't became NULL then use the value remaining + * in the view although this will be recomputated afterwords. + */ + appendStringInfo(buf_old, + ", %s = CASE WHEN %s THEN NULL ELSE %s END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_SUB, "mv", "t", count_col), + quote_qualified_identifier("mv", resname) + ); + /* count = mv.count - t.count */ + appendStringInfo(buf_old, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_SUB, count_col, "mv", "t", NULL, NULL) + ); + } + /* For tuple insertion */ + if (buf_new) + { + /* + * min = LEAST(mv.min, diff.min) + * max = GREATEST(mv.max, diff.max) + */ + appendStringInfo(buf_new, + ", %s = CASE WHEN %s THEN NULL ELSE %s(%s,%s) END", + quote_qualified_identifier(NULL, resname), + get_null_condition_string(IVM_ADD, "mv", "diff", count_col), + + is_min ? "LEAST" : "GREATEST", + quote_qualified_identifier("mv", resname), + quote_qualified_identifier("diff", resname) + ); + /* count = mv.count + diff.count */ + appendStringInfo(buf_new, + ", %s = %s", + quote_qualified_identifier(NULL, count_col), + get_operation_string(IVM_ADD, count_col, "mv", "diff", NULL, NULL) + ); + } + + appendStringInfo(aggs_list, ", %s, %s", + quote_qualified_identifier("diff", resname), + quote_qualified_identifier("diff", IVM_colname("count", resname)) + ); +} + /* * get_operation_string * @@ -2526,19 +2658,44 @@ get_null_condition_string(IvmOp op, const char *arg1, const char *arg2, * list to identify a tuple in the view. If the view has aggregates, this * requires strings representing resnames of aggregates and SET clause for * updating aggregate values. + * + * If the view has min or max aggregate, this requires a list of resnames of + * min/max aggregates and a list of boolean which represents which entries in + * minmax_list is min. These are necessary to check if we need to recalculate + * min or max aggregate values. In this case, this query returns TID and keys + * of tuples which need to be recalculated. This result and the number of rows + * are stored in tuptables and num_recalc repectedly. + * */ static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, List *keys, StringInfo aggs_list, StringInfo aggs_set, - const char *count_colname) + List *minmax_list, List *is_min_list, + const char *count_colname, + SPITupleTable **tuptable_recalc, uint64 *num_recalc) { StringInfoData querybuf; char *match_cond; + char *updt_returning = ""; + char *select_for_recalc = "SELECT"; bool agg_without_groupby = (list_length(keys) == 0); + Assert(tuptable_recalc != NULL); + Assert(num_recalc != NULL); + /* build WHERE condition for searching tuples to be deleted */ match_cond = get_matching_condition_string(keys); + /* + * We need a special RETURNING clause and SELECT statement for min/max to + * check which tuple needs re-calculation from base tables. + */ + if (minmax_list) + { + updt_returning = get_returning_string(minmax_list, is_min_list, keys); + select_for_recalc = get_select_for_recalc_string(keys); + } + /* Search for matching tuples from the view and update or delete if found. */ initStringInfo(&querybuf); appendStringInfo(&querybuf, @@ -2553,10 +2710,11 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, "UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s " "%s" /* SET clauses for aggregates */ "FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt " - ")" - /* delete a tuple if this is to be deleted */ - "DELETE FROM %s AS mv USING t " - "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt", + "%s" /* RETURNING clause for recalc infomation */ + "), dlt AS (" /* delete a tuple if this is to be deleted */ + "DELETE FROM %s AS mv USING t " + "WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt" + ") %s", /* SELECT returning which tuples need to be recalculated */ count_colname, count_colname, count_colname, (agg_without_groupby ? "false" : "true"), (aggs_list != NULL ? aggs_list->data : ""), @@ -2564,10 +2722,25 @@ apply_old_delta_with_count(const char *matviewname, const char *deltaname_old, match_cond, matviewname, count_colname, count_colname, count_colname, (aggs_set != NULL ? aggs_set->data : ""), - matviewname); + updt_returning, + matviewname, + select_for_recalc); - if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE) + if (SPI_exec(querybuf.data, 0) != SPI_OK_SELECT) elog(ERROR, "SPI_exec failed: %s", querybuf.data); + + + /* Return tuples to be recalculated. */ + if (minmax_list) + { + *tuptable_recalc = SPI_tuptable; + *num_recalc = SPI_processed; + } + else + { + *tuptable_recalc = NULL; + *num_recalc = 0; + } } /* @@ -2750,6 +2923,349 @@ get_matching_condition_string(List *keys) return match_cond.data; } +/* + * get_returning_string + * + * Build a string for RETURNING clause of UPDATE used in apply_old_delta_with_count. + * This clause returns ctid and a boolean value that indicates if we need to + * recalculate min or max value, for each updated row. + */ +static char * +get_returning_string(List *minmax_list, List *is_min_list, List *keys) +{ + StringInfoData returning; + char *recalc_cond; + ListCell *lc; + + Assert(minmax_list != NIL && is_min_list != NIL); + recalc_cond = get_minmax_recalc_condition_string(minmax_list, is_min_list); + + initStringInfo(&returning); + + appendStringInfo(&returning, "RETURNING mv.ctid AS tid, (%s) AS recalc", recalc_cond); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + appendStringInfo(&returning, ", %s", quote_qualified_identifier("mv", resname)); + } + + return returning.data; +} + +/* + * get_minmax_recalc_condition_string + * + * Build a predicate string for checking if any min/max aggregate + * value needs to be recalculated. + */ +static char * +get_minmax_recalc_condition_string(List *minmax_list, List *is_min_list) +{ + StringInfoData recalc_cond; + ListCell *lc1, *lc2; + + initStringInfo(&recalc_cond); + + Assert (list_length(minmax_list) == list_length(is_min_list)); + + forboth (lc1, minmax_list, lc2, is_min_list) + { + char *resname = (char *) lfirst(lc1); + bool is_min = (bool) lfirst_int(lc2); + char *op_str = (is_min ? ">=" : "<="); + + appendStringInfo(&recalc_cond, "%s OPERATOR(pg_catalog.%s) %s", + quote_qualified_identifier("mv", resname), + op_str, + quote_qualified_identifier("t", resname) + ); + + if (lnext(minmax_list, lc1)) + appendStringInfo(&recalc_cond, " OR "); + } + + return recalc_cond.data; +} + +/* + * get_select_for_recalc_string + * + * Build a query to return tid and keys of tuples which need + * recalculation. This is used as the result of the query + * built by apply_old_delta. + */ +static char * +get_select_for_recalc_string(List *keys) +{ + StringInfoData qry; + ListCell *lc; + + initStringInfo(&qry); + + appendStringInfo(&qry, "SELECT tid"); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + appendStringInfo(&qry, ", %s", NameStr(attr->attname)); + } + + appendStringInfo(&qry, " FROM updt WHERE recalc"); + + return qry.data; +} + +/* + * recalc_and_set_values + * + * Recalculate tuples in a materialized from base tables and update these. + * The tuples which needs recalculation are specified by keys, and resnames + * of columns to be updated are specified by namelist. TIDs and key values + * are given by tuples in tuptable_recalc. Its first attribute must be TID + * and key values must be following this. + */ +static void +recalc_and_set_values(SPITupleTable *tuptable_recalc, int64 num_tuples, + List *namelist, List *keys, Relation matviewRel) +{ + TupleDesc tupdesc_recalc = tuptable_recalc->tupdesc; + Oid *keyTypes = NULL, *types = NULL; + char *keyNulls = NULL, *nulls = NULL; + Datum *keyVals = NULL, *vals = NULL; + int num_vals = list_length(namelist); + int num_keys = list_length(keys); + uint64 i; + Oid matviewOid; + char *matviewname; + + matviewOid = RelationGetRelid(matviewRel); + matviewname = quote_qualified_identifier(get_namespace_name(RelationGetNamespace(matviewRel)), + RelationGetRelationName(matviewRel)); + + /* If we have keys, initialize arrays for them. */ + if (keys) + { + keyTypes = palloc(sizeof(Oid) * num_keys); + keyNulls = palloc(sizeof(char) * num_keys); + keyVals = palloc(sizeof(Datum) * num_keys); + /* a tuple contains keys to be recalculated and ctid to be updated*/ + Assert(tupdesc_recalc->natts == num_keys + 1); + + /* Types of key attributes */ + for (i = 0; i < num_keys; i++) + keyTypes[i] = TupleDescAttr(tupdesc_recalc, i + 1)->atttypid; + } + + /* allocate memory for all attribute names and tid */ + types = palloc(sizeof(Oid) * (num_vals + 1)); + nulls = palloc(sizeof(char) * (num_vals + 1)); + vals = palloc(sizeof(Datum) * (num_vals + 1)); + + /* For each tuple which needs recalculation */ + for (i = 0; i < num_tuples; i++) + { + int j; + bool isnull; + SPIPlanPtr plan; + SPITupleTable *tuptable_newvals; + TupleDesc tupdesc_newvals; + + /* Set group key values as parameters if needed. */ + if (keys) + { + for (j = 0; j < num_keys; j++) + { + keyVals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, j + 2, &isnull); + if (isnull) + keyNulls[j] = 'n'; + else + keyNulls[j] = ' '; + } + } + + /* + * Get recalculated values from base tables. The result must be + * only one tuple thich contains the new values for specified keys. + */ + plan = get_plan_for_recalc(matviewOid, namelist, keys, keyTypes); + if (SPI_execute_plan(plan, keyVals, keyNulls, false, 0) != SPI_OK_SELECT) + elog(ERROR, "SPI_execute_plan"); + if (SPI_processed != 1) + elog(ERROR, "SPI_execute_plan returned zero or more than one rows"); + + tuptable_newvals = SPI_tuptable; + tupdesc_newvals = tuptable_newvals->tupdesc; + + Assert(tupdesc_newvals->natts == num_vals); + + /* Set the new values as parameters */ + for (j = 0; j < tupdesc_newvals->natts; j++) + { + if (i == 0) + types[j] = TupleDescAttr(tupdesc_newvals, j)->atttypid; + + vals[j] = SPI_getbinval(tuptable_newvals->vals[0], tupdesc_newvals, j + 1, &isnull); + if (isnull) + nulls[j] = 'n'; + else + nulls[j] = ' '; + } + /* Set TID of the view tuple to be updated as a parameter */ + types[j] = TIDOID; + vals[j] = SPI_getbinval(tuptable_recalc->vals[i], tupdesc_recalc, 1, &isnull); + nulls[j] = ' '; + + /* Update the view tuple to the new values */ + plan = get_plan_for_set_values(matviewOid, matviewname, namelist, types); + if (SPI_execute_plan(plan, vals, nulls, false, 0) != SPI_OK_UPDATE) + elog(ERROR, "SPI_execute_plan"); + } +} + + +/* + * get_plan_for_recalc + * + * Create or fetch a plan for recalculating value in the view's target list + * from base tables using the definition query of materialized view specified + * by matviewOid. namelist is a list of resnames of values to be recalculated. + * + * keys is a list of keys to identify tuples to be recalculated if this is not + * empty. KeyTypes is an array of types of keys. + */ +static SPIPlanPtr +get_plan_for_recalc(Oid matviewOid, List *namelist, List *keys, Oid *keyTypes) +{ + MV_QueryKey hash_key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the recalculation */ + mv_BuildQueryKey(&hash_key, matviewOid, MV_PLAN_RECALC); + if ((plan = mv_FetchPreparedPlan(&hash_key)) == NULL) + { + ListCell *lc; + StringInfoData str; + char *viewdef; + + /* get view definition of matview */ + viewdef = text_to_cstring((text *) DatumGetPointer( + DirectFunctionCall1(pg_get_viewdef, ObjectIdGetDatum(matviewOid)))); + /* get rid of trailing semi-colon */ + viewdef[strlen(viewdef)-1] = '\0'; + + /* + * Build a query string for recalculating values. This is like + * + * SELECT x1, x2, x3, ... FROM ( ... view definition query ...) mv + * WHERE (key1, key2, ...) = ($1, $2, ...); + */ + + initStringInfo(&str); + appendStringInfo(&str, "SELECT "); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, " FROM (%s) mv", viewdef); + + if (keys) + { + int i = 1; + char paramname[16]; + + appendStringInfo(&str, " WHERE ("); + foreach (lc, keys) + { + Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc); + char *resname = NameStr(attr->attname); + Oid typid = attr->atttypid; + + sprintf(paramname, "$%d", i); + appendStringInfo(&str, "("); + generate_equal(&str, typid, resname, paramname); + appendStringInfo(&str, " OR (%s IS NULL AND %s IS NULL))", + resname, paramname); + + if (lnext(keys, lc)) + appendStringInfoString(&str, " AND "); + i++; + } + appendStringInfo(&str, ")"); + } + else + keyTypes = NULL; + + plan = SPI_prepare(str.data, list_length(keys), keyTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&hash_key, plan); + } + + return plan; +} + +/* + * get_plan_for_set_values + * + * Create or fetch a plan for applying new values calculated by + * get_plan_for_recalc to a materialized view specified by matviewOid. + * matviewname is the name of the view. namelist is a list of resnames + * of attributes to be updated, and valTypes is an array of types of the + * values. + */ +static SPIPlanPtr +get_plan_for_set_values(Oid matviewOid, char *matviewname, List *namelist, + Oid *valTypes) +{ + MV_QueryKey key; + SPIPlanPtr plan; + + /* Fetch or prepare a saved plan for the real check */ + mv_BuildQueryKey(&key, matviewOid, MV_PLAN_SET_VALUE); + if ((plan = mv_FetchPreparedPlan(&key)) == NULL) + { + ListCell *lc; + StringInfoData str; + int i; + + /* + * Build a query string for applying min/max values. This is like + * + * UPDATE matviewname AS mv + * SET (x1, x2, x3, x4) = ($1, $2, $3, $4) + * WHERE ctid = $5; + */ + + initStringInfo(&str); + appendStringInfo(&str, "UPDATE %s AS mv SET (", matviewname); + foreach (lc, namelist) + { + appendStringInfo(&str, "%s", (char *) lfirst(lc)); + if (lnext(namelist, lc)) + appendStringInfoString(&str, ", "); + } + appendStringInfo(&str, ") = ROW("); + + for (i = 1; i <= list_length(namelist); i++) + appendStringInfo(&str, "%s$%d", (i==1 ? "" : ", "), i); + + appendStringInfo(&str, ") WHERE ctid OPERATOR(pg_catalog.=) $%d", i); + + plan = SPI_prepare(str.data, list_length(namelist) + 1, valTypes); + if (plan == NULL) + elog(ERROR, "SPI_prepare returned %s for %s", SPI_result_code_string(SPI_result), str.data); + + SPI_keepplan(plan); + mv_HashPreparedPlan(&key, plan); + } + + return plan; +} + /* * generate_equals * @@ -2783,6 +3299,13 @@ mv_InitHashTables(void) { HASHCTL ctl; + memset(&ctl, 0, sizeof(ctl)); + ctl.keysize = sizeof(MV_QueryKey); + ctl.entrysize = sizeof(MV_QueryHashEntry); + mv_query_cache = hash_create("MV query cache", + MV_INIT_QUERYHASHSIZE, + &ctl, HASH_ELEM | HASH_BLOBS); + memset(&ctl, 0, sizeof(ctl)); ctl.keysize = sizeof(Oid); ctl.entrysize = sizeof(MV_TriggerHashEntry); @@ -2791,6 +3314,109 @@ mv_InitHashTables(void) &ctl, HASH_ELEM | HASH_BLOBS); } +/* + * mv_FetchPreparedPlan + */ +static SPIPlanPtr +mv_FetchPreparedPlan(MV_QueryKey *key) +{ + MV_QueryHashEntry *entry; + SPIPlanPtr plan; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Lookup for the key + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_FIND, NULL); + if (entry == NULL) + return NULL; + + /* + * Check whether the plan is still valid. If it isn't, we don't want to + * simply rely on plancache.c to regenerate it; rather we should start + * from scratch and rebuild the query text too. This is to cover cases + * such as table/column renames. We depend on the plancache machinery to + * detect possible invalidations, though. + * + * CAUTION: this check is only trustworthy if the caller has already + * locked both materialized views and base tables. + * + * Also, check whether the search_path is still the same as when we made it. + * If it isn't, we need to rebuild the query text because the result of + * pg_ivm_get_viewdef() will change. + */ + plan = entry->plan; + if (plan && SPI_plan_is_valid(plan) && + SearchPathMatchesCurrentEnvironment(entry->search_path)) + return plan; + + /* + * Otherwise we might as well flush the cached plan now, to free a little + * memory space before we make a new one. + */ + if (plan) + SPI_freeplan(plan); + if (entry->search_path) + pfree(entry->search_path); + + entry->plan = NULL; + entry->search_path = NULL; + + return NULL; +} + +/* + * mv_HashPreparedPlan + * + * Add another plan to our private SPI query plan hashtable. + */ +static void +mv_HashPreparedPlan(MV_QueryKey *key, SPIPlanPtr plan) +{ + MV_QueryHashEntry *entry; + bool found; + + /* + * On the first call initialize the hashtable + */ + if (!mv_query_cache) + mv_InitHashTables(); + + /* + * Add the new plan. We might be overwriting an entry previously found + * invalid by mv_FetchPreparedPlan. + */ + entry = (MV_QueryHashEntry *) hash_search(mv_query_cache, + (void *) key, + HASH_ENTER, &found); + Assert(!found || entry->plan == NULL); + entry->plan = plan; + entry->search_path = GetSearchPathMatcher(TopMemoryContext); +} + +/* + * mv_BuildQueryKey + * + * Construct a hashtable key for a prepared SPI plan for IVM. + */ +static void +mv_BuildQueryKey(MV_QueryKey *key, Oid matview_id, int32 query_type) +{ + /* + * We assume struct MV_QueryKey contains no padding bytes, else we'd need + * to use memset to clear them. + */ + key->matview_id = matview_id; + key->query_type = query_type; +} + /* * AtAbort_IVM * -- 2.25.1 --Multipart=_Mon__28_Aug_2023_16_05_30_+0900_b1OvQD_3A3ZMTGvj Content-Type: text/x-diff; name="v29-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Disposition: attachment; filename="v29-0010-Add-regression-tests-for-Incremental-View-Mainte.patch" Content-Transfer-Encoding: 7bit ^ permalink raw reply [nested|flat] 259+ messages in thread
* [PATCH v15 2/2] handle relation statistics correctly during rewrites @ 2025-11-04 13:52 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 259+ messages in thread From: Bertrand Drouvot @ 2025-11-04 13:52 UTC (permalink / raw) Now that PGSTAT_KIND_RELATION is keyed by refilenode, we need to handle rewrites. To do so, this patch: - Adds PgStat_PendingRewrite, a new struct to track rewrite operations within a transaction, storing the old locator, new locator, and original locator (for rewrite chains). This allows stats to be copied from the original location to the final location at commit time. - Adds a new function, pgstat_mark_rewrite(), called when a table rewrite begins. It records the rewrite operation in a local list and detects rewrite chains by checking if the old_locator matches any existing new_locator, preserving the chain's original_locator. - Modifies pgstat_copy_relation_stats(), to accept RelFileLocators instead of Relations, with a new increment parameter to accumulate stats (needed for rewrite chains with DML between rewrites). - Ensures that AtEOXact_PgStat_Relations(), AtPrepare_PgStat_Relations(), pgstat_twophase_postcommit()/postabort() pgstat_drop_relation() handle the PgStat_PendingRewrite list correctly. Note that due to the new flush call in pgstat_twophase_postcommit() we can not call GetCurrentTransactionStopTimestamp() in pgstat_relation_flush_cb(). So, adding a check to handle this special case and call GetCurrentTimestamp() instead. Note that we'd call GetCurrentTimestamp() only if there is a rewrite, so that the GetCurrentTimestamp() extra cost should be negligible. Another solution could be to trigger the flush from FinishPreparedTransaction() but that's not worth the extra complexity. The new pending_rewrites list is traversed in multiple places. The overhead should be negligible in comparison to a rewrite and the list should not contain a lot of rewrites in practice. The pending_rewrites list is traversed in multiple places. In typical usage, the list will contain only a few entries so the traversal cost is negligible ( furthermore in comparison to a rewrite). --- src/backend/catalog/index.c | 2 +- src/backend/commands/cluster.c | 5 + src/backend/commands/tablecmds.c | 6 + src/backend/utils/activity/pgstat_relation.c | 391 ++++++++++++++++++- src/backend/utils/activity/pgstat_xact.c | 25 +- src/backend/utils/cache/relcache.c | 6 + src/include/pgstat.h | 5 +- src/tools/pgindent/typedefs.list | 1 + 8 files changed, 424 insertions(+), 17 deletions(-) 92.8% src/backend/utils/activity/ 4.9% src/backend/ diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c index 1ccfa687f05..e292199ca7c 100644 --- a/src/backend/catalog/index.c +++ b/src/backend/catalog/index.c @@ -1796,7 +1796,7 @@ index_concurrently_swap(Oid newIndexId, Oid oldIndexId, const char *oldName) changeDependenciesOn(RelationRelationId, oldIndexId, newIndexId); /* copy over statistics from old to new index */ - pgstat_copy_relation_stats(newClassRel, oldClassRel); + pgstat_copy_relation_stats(newClassRel->rd_locator, oldClassRel->rd_locator, false); /* Copy data of pg_statistic from the old index to the new one */ CopyStatistics(oldIndexId, newIndexId); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 09066db0956..c491daceb0f 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1206,6 +1206,11 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class, rel1 = relation_open(r1, NoLock); rel2 = relation_open(r2, NoLock); + + /* Mark that a rewrite happened */ + if (RELKIND_HAS_STORAGE(rel1->rd_rel->relkind)) + pgstat_mark_rewrite(rel1->rd_locator, rel2->rd_locator); + rel2->rd_createSubid = rel1->rd_createSubid; rel2->rd_newRelfilelocatorSubid = rel1->rd_newRelfilelocatorSubid; rel2->rd_firstRelfilelocatorSubid = rel1->rd_firstRelfilelocatorSubid; diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c index 8b4ebc6f226..49de04d9697 100644 --- a/src/backend/commands/tablecmds.c +++ b/src/backend/commands/tablecmds.c @@ -17102,6 +17102,7 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode) Oid reltoastrelid; RelFileNumber newrelfilenumber; RelFileLocator newrlocator; + RelFileLocator oldrlocator; List *reltoastidxids = NIL; ListCell *lc; @@ -17140,6 +17141,7 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode) newrlocator = rel->rd_locator; newrlocator.relNumber = newrelfilenumber; newrlocator.spcOid = newTableSpace; + oldrlocator = rel->rd_locator; /* hand off to AM to actually create new rel storage and copy the data */ if (rel->rd_rel->relkind == RELKIND_INDEX) @@ -17152,6 +17154,10 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode) table_relation_copy_data(rel, &newrlocator); } + /* mark that a rewrite happened */ + if (RELKIND_HAS_STORAGE(rel->rd_rel->relkind)) + pgstat_mark_rewrite(oldrlocator, newrlocator); + /* * Update the pg_class row. * diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c index 89bf0cbed56..4d929972fab 100644 --- a/src/backend/utils/activity/pgstat_relation.c +++ b/src/backend/utils/activity/pgstat_relation.c @@ -30,6 +30,19 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +/* Pending rewrite operations for stats copying */ +typedef struct PgStat_PendingRewrite +{ + RelFileLocator old_locator; + RelFileLocator new_locator; + RelFileLocator original_locator; + int nest_level; /* Transaction nesting level where rewrite + * occurred */ + struct PgStat_PendingRewrite *next; +} PgStat_PendingRewrite; + +/* The pending rewrites list for current transaction */ +static PgStat_PendingRewrite *pending_rewrites = NULL; /* Record that's written to 2PC state file when pgstat state is persisted */ typedef struct TwoPhasePgStatRecord @@ -43,6 +56,8 @@ typedef struct TwoPhasePgStatRecord PgStat_Counter deleted_pre_truncdrop; RelFileLocator locator; /* table's rd_locator */ bool truncdropped; /* was the relation truncated/dropped? */ + RelFileLocator rewrite_old_locator; + int rewrite_nest_level; } TwoPhasePgStatRecord; @@ -54,27 +69,70 @@ static void restore_truncdrop_counters(PgStat_TableXactStatus *trans); /* - * Copy stats between relations. This is used for things like REINDEX + * Copy stats between RelFileLocator. This is used for things like REINDEX * CONCURRENTLY. */ void -pgstat_copy_relation_stats(Relation dst, Relation src) +pgstat_copy_relation_stats(RelFileLocator dst, RelFileLocator src, bool increment) { PgStat_StatTabEntry *srcstats; PgStatShared_Relation *dstshstats; PgStat_EntryRef *dst_ref; - srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src)); + srcstats = (PgStat_StatTabEntry *) pgstat_fetch_entry(PGSTAT_KIND_RELATION, + src.dbOid, + RelFileLocatorToPgStatObjid(src)); if (!srcstats) return; dst_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, - dst->rd_rel->relisshared ? InvalidOid : MyDatabaseId, - RelationGetRelid(dst), + dst.dbOid, + RelFileLocatorToPgStatObjid(dst), false); dstshstats = (PgStatShared_Relation *) dst_ref->shared_stats; - dstshstats->stats = *srcstats; + + if (!increment) + dstshstats->stats = *srcstats; + else + { + /* Increment those statistics */ +#define RELFSTAT_ACC(fld, stats_to_add) \ + (dstshstats->stats.fld += stats_to_add->fld) + RELFSTAT_ACC(numscans, srcstats); + RELFSTAT_ACC(tuples_returned, srcstats); + RELFSTAT_ACC(tuples_fetched, srcstats); + RELFSTAT_ACC(tuples_inserted, srcstats); + RELFSTAT_ACC(tuples_updated, srcstats); + RELFSTAT_ACC(tuples_deleted, srcstats); + RELFSTAT_ACC(tuples_hot_updated, srcstats); + RELFSTAT_ACC(tuples_newpage_updated, srcstats); + RELFSTAT_ACC(live_tuples, srcstats); + RELFSTAT_ACC(dead_tuples, srcstats); + RELFSTAT_ACC(mod_since_analyze, srcstats); + RELFSTAT_ACC(ins_since_vacuum, srcstats); + RELFSTAT_ACC(blocks_fetched, srcstats); + RELFSTAT_ACC(blocks_hit, srcstats); + RELFSTAT_ACC(vacuum_count, srcstats); + RELFSTAT_ACC(autovacuum_count, srcstats); + RELFSTAT_ACC(analyze_count, srcstats); + RELFSTAT_ACC(autoanalyze_count, srcstats); + RELFSTAT_ACC(total_vacuum_time, srcstats); + RELFSTAT_ACC(total_autovacuum_time, srcstats); + RELFSTAT_ACC(total_analyze_time, srcstats); + RELFSTAT_ACC(total_autoanalyze_time, srcstats); +#undef RELFSTAT_ACC + + /* Replace those statistics */ +#define RELFSTAT_REP(fld, stats_to_rep) \ + (dstshstats->stats.fld = stats_to_rep->fld) + RELFSTAT_REP(lastscan, srcstats); + RELFSTAT_REP(last_vacuum_time, srcstats); + RELFSTAT_REP(last_autovacuum_time, srcstats); + RELFSTAT_REP(last_analyze_time, srcstats); + RELFSTAT_REP(last_autoanalyze_time, srcstats); +#undef RELFSTAT_REP + } pgstat_unlock_entry(dst_ref); } @@ -136,6 +194,7 @@ void pgstat_assoc_relation(Relation rel) { RelFileLocator locator; + PgStat_TableStatus *pgstat_info; Assert(rel->pgstat_enabled); Assert(rel->pgstat_info == NULL); @@ -164,14 +223,54 @@ pgstat_assoc_relation(Relation rel) locator.relNumber = rel->rd_id; } + /* + * If this relation was rewritten during the current transaction we may be + * reopening it with its new RelFileLocator. In that case, continue using + * the stats entry associated with the old locator rather than creating a + * new one. This ensures all stats from before and after the rewrite are + * tracked in a single entry which will be properly copied to the new + * locator at transaction commit. + */ + if (pending_rewrites != NULL) + { + PgStat_PendingRewrite *rewrite; + + for (rewrite = pending_rewrites; rewrite != NULL; rewrite = rewrite->next) + { + if (locator.dbOid == rewrite->new_locator.dbOid && + locator.spcOid == rewrite->new_locator.spcOid && + locator.relNumber == rewrite->new_locator.relNumber) + { + pgstat_info = pgstat_prep_relation_pending(rewrite->old_locator); + goto found_entry; + } + } + } + /* Else find or make the PgStat_TableStatus entry, and update link */ - rel->pgstat_info = pgstat_prep_relation_pending(locator); + pgstat_info = pgstat_prep_relation_pending(locator); + +found_entry: + rel->pgstat_info = pgstat_info; + + /* + * For relations stats, we key by physical file location, not by relation + * OID. This means during operations like ALTER TYPE it's possible that + * the relation OID changes but the relfilenode stays the same (no actual + * rewrite needed). Unlink the old relation first. + */ + if (pgstat_info->relation != NULL && + pgstat_info->relation != rel) + { + pgstat_info->relation->pgstat_info = NULL; + pgstat_info->relation = NULL; + } /* don't allow link a stats to multiple relcache entries */ - Assert(rel->pgstat_info->relation == NULL); + Assert(pgstat_info->relation == NULL); /* mark this relation as the owner */ - rel->pgstat_info->relation = rel; + pgstat_info->relation = rel; } /* @@ -214,14 +313,37 @@ pgstat_drop_relation(Relation rel) { int nest_level = GetCurrentTransactionNestLevel(); PgStat_TableStatus *pgstat_info; + bool skip_transactional_drop = false; /* don't track stats for relations without storage */ if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind)) return; - pgstat_drop_transactional(PGSTAT_KIND_RELATION, - rel->rd_locator.dbOid, - RelFileLocatorToPgStatObjid(rel->rd_locator)); + /* Check if this drop is part of a pending rewrite */ + if (pending_rewrites != NULL) + { + PgStat_PendingRewrite *rewrite; + + for (rewrite = pending_rewrites; rewrite != NULL; rewrite = rewrite->next) + { + if (rel->rd_locator.dbOid == rewrite->old_locator.dbOid && + rel->rd_locator.spcOid == rewrite->old_locator.spcOid && + rel->rd_locator.relNumber == rewrite->old_locator.relNumber) + { + skip_transactional_drop = true; + break; + } + } + } + + /* + * If it is part of a rewrite, drop its stats later, for example in + * AtEOXact_PgStat_Relations(), so skip it here. + */ + if (!skip_transactional_drop) + pgstat_drop_transactional(PGSTAT_KIND_RELATION, + rel->rd_locator.dbOid, + RelFileLocatorToPgStatObjid(rel->rd_locator)); if (!pgstat_should_count_relation(rel)) return; @@ -666,6 +788,48 @@ AtEOXact_PgStat_Relations(PgStat_SubXactStatus *xact_state, bool isCommit) } tabstat->trans = NULL; } + + /* preserve the stats in case of rewrite */ + if (isCommit && pending_rewrites != NULL) + { + PgStat_PendingRewrite *rewrite; + PgStat_PendingRewrite *prev = NULL; + PgStat_PendingRewrite *current = pending_rewrites; + PgStat_PendingRewrite *next; + + /* reverse the rewrites list to process in chronological order */ + while (current != NULL) + { + next = current->next; + current->next = prev; + prev = current; + current = next; + } + + /* now process rewrites in chronological order */ + for (rewrite = prev; rewrite != NULL; rewrite = rewrite->next) + { + PgStat_EntryRef *old_entry_ref; + + old_entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, + rewrite->old_locator.dbOid, + RelFileLocatorToPgStatObjid(rewrite->old_locator)); + + if (old_entry_ref && old_entry_ref->pending) + pgstat_relation_flush_cb(old_entry_ref, false); + + pgstat_copy_relation_stats(rewrite->new_locator, + rewrite->old_locator, true); + + /* drop old locator's stats */ + if (!pgstat_drop_entry(PGSTAT_KIND_RELATION, + rewrite->old_locator.dbOid, + RelFileLocatorToPgStatObjid(rewrite->old_locator))) + pgstat_request_entry_refs_gc(); + } + } + + pending_rewrites = NULL; } /* @@ -681,6 +845,30 @@ AtEOSubXact_PgStat_Relations(PgStat_SubXactStatus *xact_state, bool isCommit, in PgStat_TableXactStatus *trans; PgStat_TableXactStatus *next_trans; + /* + * If we don't commit then remove the associated rewrites if any, to keep + * the rewrite chain in sync with what will be eventually committed. + */ + if (!isCommit) + { + PgStat_PendingRewrite **rewrite_ptr = &pending_rewrites; + + while (*rewrite_ptr != NULL) + { + if ((*rewrite_ptr)->nest_level >= nestDepth) + { + PgStat_PendingRewrite *to_remove = *rewrite_ptr; + + *rewrite_ptr = (*rewrite_ptr)->next; + pfree(to_remove); + } + else + { + rewrite_ptr = &((*rewrite_ptr)->next); + } + } + } + for (trans = xact_state->first; trans != NULL; trans = next_trans) { PgStat_TableStatus *tabstat; @@ -760,11 +948,19 @@ void AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state) { PgStat_TableXactStatus *trans; + PgStat_PendingRewrite *rewrite; + /* + * For each tabstat, find its matching rewrite and remove it from the + * pending rewrites list. This way, after processing all tabstats, pending + * rewrites will only contain rewrite only transactions. + */ for (trans = xact_state->first; trans != NULL; trans = trans->next) { PgStat_TableStatus *tabstat PG_USED_FOR_ASSERTS_ONLY; TwoPhasePgStatRecord record; + PgStat_PendingRewrite **rewrite_ptr; + bool found_rewrite = false; Assert(trans->nest_level == 1); Assert(trans->upper == NULL); @@ -784,10 +980,83 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state) record.locator = tabstat->locator; record.truncdropped = trans->truncdropped; + record.rewrite_nest_level = 0; + + /* + * Look for a matching rewrite and remove it from pending rewrites. We + * check three possible matches: + * + * The new_locator when stats have been added after the rewrite. The + * old_locator when stats have been added before the rewrite but not + * after. The original_locator when this tabstat is part of a rewrite + * chain. + */ + rewrite_ptr = &pending_rewrites; + while (*rewrite_ptr != NULL) + { + rewrite = *rewrite_ptr; + + if ((record.locator.dbOid == rewrite->new_locator.dbOid && + record.locator.spcOid == rewrite->new_locator.spcOid && + record.locator.relNumber == rewrite->new_locator.relNumber) || + (tabstat->locator.dbOid == rewrite->old_locator.dbOid && + tabstat->locator.spcOid == rewrite->old_locator.spcOid && + tabstat->locator.relNumber == rewrite->old_locator.relNumber) || + (tabstat->locator.dbOid == rewrite->original_locator.dbOid && + tabstat->locator.spcOid == rewrite->original_locator.spcOid && + tabstat->locator.relNumber == rewrite->original_locator.relNumber)) + { + /* + * Found matching rewrite. Record the rewrite information and + * remove this rewrite from the list since it's now handled. + */ + record.rewrite_old_locator = rewrite->original_locator; + record.rewrite_nest_level = rewrite->nest_level; + record.locator = rewrite->new_locator; + found_rewrite = true; + + /* Remove from pending_rewrites list */ + *rewrite_ptr = rewrite->next; + pfree(rewrite); + break; + } + else + { + /* Move to next rewrite in the list */ + rewrite_ptr = &(rewrite->next); + } + } + + /* If no rewrite found, clear the rewrite fields */ + if (!found_rewrite) + { + memset(&record.rewrite_old_locator, 0, sizeof(RelFileLocator)); + } + + RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0, + &record, sizeof(TwoPhasePgStatRecord)); + } + + /* + * Now process any rewrites still pending. These are rewrite only + * transactions. We need to preserve their stats even though there's no + * tabstat entry for them. + */ + for (rewrite = pending_rewrites; rewrite != NULL; rewrite = rewrite->next) + { + TwoPhasePgStatRecord record; + + memset(&record, 0, sizeof(TwoPhasePgStatRecord)); + record.locator = rewrite->new_locator; + record.rewrite_old_locator = rewrite->original_locator; + record.rewrite_nest_level = rewrite->nest_level; + record.truncdropped = false; RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0, &record, sizeof(TwoPhasePgStatRecord)); } + + pending_rewrites = NULL; } /* @@ -810,6 +1079,8 @@ PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state) tabstat = trans->parent; tabstat->trans = NULL; } + + pending_rewrites = NULL; } /* @@ -845,6 +1116,29 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info, pgstat_info->counts.changed_tuples += rec->tuples_inserted + rec->tuples_updated + rec->tuples_deleted; + + if (rec->rewrite_nest_level > 0) + { + PgStat_EntryRef *old_entry_ref; + + /* Flush any pending stats for old locator first */ + old_entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, + rec->rewrite_old_locator.dbOid, + RelFileLocatorToPgStatObjid(rec->rewrite_old_locator)); + + if (old_entry_ref && old_entry_ref->pending) + pgstat_relation_flush_cb(old_entry_ref, false); + + /* Copy stats from old to new locator */ + pgstat_copy_relation_stats(rec->locator, rec->rewrite_old_locator, + true); + + /* Drop old locator's stats */ + if (!pgstat_drop_entry(PGSTAT_KIND_RELATION, + rec->rewrite_old_locator.dbOid, + RelFileLocatorToPgStatObjid(rec->rewrite_old_locator))) + pgstat_request_entry_refs_gc(); + } } /* @@ -859,9 +1153,26 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info, { TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata; PgStat_TableStatus *pgstat_info; + RelFileLocator target_locator; + + /* + * For aborted transactions with rewrites (like TRUNCATE), we need to + * restore stats to the old locator, not the new one. The new locator + * should be dropped since the rewrite is being rolled back. + */ + if (rec->rewrite_nest_level > 0) + { + /* Use the old locator */ + target_locator = rec->rewrite_old_locator; + } + else + { + /* No rewrite, use the original locator */ + target_locator = rec->locator; + } /* Find or create a tabstat entry for the target locator */ - pgstat_info = pgstat_prep_relation_pending(rec->locator); + pgstat_info = pgstat_prep_relation_pending(target_locator); /* Same math as in AtEOXact_PgStat, abort case */ if (rec->truncdropped) @@ -916,7 +1227,17 @@ pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait) tabentry->numscans += lstats->counts.numscans; if (lstats->counts.numscans) { - TimestampTz t = GetCurrentTransactionStopTimestamp(); + TimestampTz t; + + /* + * Checking the transaction state due to the flush call in + * pgstat_twophase_postcommit() that would break the assertion on the + * state in GetCurrentTransactionStopTimestamp(). + */ + if (!IsTransactionState()) + t = GetCurrentTransactionStopTimestamp(); + else + t = GetCurrentTimestamp(); if (t > tabentry->lastscan) tabentry->lastscan = t; @@ -1167,3 +1488,45 @@ pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator) ReleaseSysCache(tuple); return result; } + +/* + * Mark that a relation rewrite has occurred, preserving the original locator + * so stats can be copied at transaction commit. + */ +void +pgstat_mark_rewrite(RelFileLocator old_locator, RelFileLocator new_locator) +{ + PgStat_PendingRewrite *rewrite; + PgStat_PendingRewrite *existing; + RelFileLocator original_locator = old_locator; + + for (existing = pending_rewrites; existing != NULL; existing = existing->next) + { + if (old_locator.dbOid == existing->new_locator.dbOid && + old_locator.spcOid == existing->new_locator.spcOid && + old_locator.relNumber == existing->new_locator.relNumber) + { + original_locator = existing->original_locator; + break; + } + } + + /* Allocate in TopTransactionContext memory context */ + rewrite = MemoryContextAlloc(TopTransactionContext, + sizeof(PgStat_PendingRewrite)); + + rewrite->old_locator = old_locator; + rewrite->new_locator = new_locator; + rewrite->original_locator = original_locator; + rewrite->nest_level = GetCurrentTransactionNestLevel(); + + /* Add to the list */ + rewrite->next = pending_rewrites; + pending_rewrites = rewrite; +} + +void +pgstat_clear_rewrite(void) +{ + pending_rewrites = NULL; +} diff --git a/src/backend/utils/activity/pgstat_xact.c b/src/backend/utils/activity/pgstat_xact.c index 5e2d69e6297..8ed8f5317f3 100644 --- a/src/backend/utils/activity/pgstat_xact.c +++ b/src/backend/utils/activity/pgstat_xact.c @@ -55,6 +55,8 @@ AtEOXact_PgStat(bool isCommit, bool parallel) } pgStatXactStack = NULL; + pgstat_clear_rewrite(); + /* Make sure any stats snapshot is thrown away */ pgstat_clear_snapshot(); } @@ -360,8 +362,29 @@ create_drop_transactional_internal(PgStat_Kind kind, Oid dboid, uint64 objid, bo void pgstat_create_transactional(PgStat_Kind kind, Oid dboid, uint64 objid) { - if (pgstat_get_entry_ref(kind, dboid, objid, false, NULL)) + PgStat_EntryRef *entry_ref; + + entry_ref = pgstat_get_entry_ref(kind, dboid, objid, false, NULL); + + if (entry_ref) { + /* + * For relations stats, we key by physical file location, not by + * relation OID. This means during operations like ALTER TYPE where + * the relation OID changes but the relfilenode stays the same (no + * actual rewrite needed), we'll find an existing entry. + * + * This is expected behavior, we want to preserve stats across the + * catalog change. Simply reset and recreate the entry for the new + * relation OID without warning. + */ + if (kind == PGSTAT_KIND_RELATION) + { + pgstat_reset(kind, dboid, objid); + create_drop_transactional_internal(kind, dboid, objid, true); + return; + } + ereport(WARNING, errmsg("resetting existing statistics for kind %s, db=%u, oid=%" PRIu64, (pgstat_get_kind_info(kind))->name, dboid, diff --git a/src/backend/utils/cache/relcache.c b/src/backend/utils/cache/relcache.c index e19f0d3e51c..bf49830dba2 100644 --- a/src/backend/utils/cache/relcache.c +++ b/src/backend/utils/cache/relcache.c @@ -87,6 +87,7 @@ #include "utils/inval.h" #include "utils/lsyscache.h" #include "utils/memutils.h" +#include "utils/pgstat_internal.h" #include "utils/relmapper.h" #include "utils/resowner.h" #include "utils/snapmgr.h" @@ -3772,6 +3773,7 @@ RelationSetNewRelfilenumber(Relation relation, char persistence) MultiXactId minmulti = InvalidMultiXactId; TransactionId freezeXid = InvalidTransactionId; RelFileLocator newrlocator; + RelFileLocator oldrlocator = relation->rd_locator; if (!IsBinaryUpgrade) { @@ -3943,6 +3945,10 @@ RelationSetNewRelfilenumber(Relation relation, char persistence) table_close(pg_class, RowExclusiveLock); + /* Mark that a rewrite happened */ + if (RELKIND_HAS_STORAGE(relation->rd_rel->relkind)) + pgstat_mark_rewrite(oldrlocator, newrlocator); + /* * Make the pg_class row change or relation map change visible. This will * cause the relcache entry to get updated, too. diff --git a/src/include/pgstat.h b/src/include/pgstat.h index ef740aff26e..4d3130ae99e 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -701,7 +701,7 @@ extern PgStat_FunctionCounts *find_funcstat_entry(Oid func_id); extern void pgstat_create_relation(Relation rel); extern void pgstat_drop_relation(Relation rel); -extern void pgstat_copy_relation_stats(Relation dst, Relation src); +extern void pgstat_copy_relation_stats(RelFileLocator dst, RelFileLocator src, bool increment); extern void pgstat_init_relation(Relation rel); extern void pgstat_assoc_relation(Relation rel); @@ -713,6 +713,9 @@ extern void pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples, extern void pgstat_report_analyze(Relation rel, PgStat_Counter livetuples, PgStat_Counter deadtuples, bool resetcounter, TimestampTz starttime); +extern void pgstat_mark_rewrite(RelFileLocator old_locator, + RelFileLocator new_locator); +extern void pgstat_clear_rewrite(void); /* * If stats are enabled, but pending data hasn't been prepared yet, call diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index c9da1f91cb9..53c94382a8d 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2314,6 +2314,7 @@ PgStat_LockEntry PgStat_PendingDroppedStatsItem PgStat_PendingIO PgStat_PendingLock +PgStat_PendingRewrite PgStat_SLRUStats PgStat_ShmemControl PgStat_Snapshot -- 2.34.1 --Og8T0Lf2JVsuKOzn-- ^ permalink raw reply [nested|flat] 259+ messages in thread
end of thread, other threads:[~2025-11-04 13:52 UTC | newest] Thread overview: 259+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v28 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v33 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v29 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v32 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v29 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v34 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v30 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v31 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v38 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2023-05-31 11:58 [PATCH v37 09/11] Add support for min/max aggregates for IVM Yugo Nagata <[email protected]> 2025-11-04 13:52 [PATCH v15 2/2] handle relation statistics correctly during rewrites Bertrand Drouvot <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox